Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.

Berlincioni, L., Becattini, F., Seidenari, L., Del Bimbo, A. (2020). Multiple future prediction leveraging synthetic trajectories. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp.6081-6088). New York : Institute of Electrical and Electronics Engineers Inc. [10.1109/ICPR48806.2021.9412158].

Multiple future prediction leveraging synthetic trajectories

Becattini F.
;
2020-01-01

Abstract

Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.
2020
978-1-7281-8808-9
Berlincioni, L., Becattini, F., Seidenari, L., Del Bimbo, A. (2020). Multiple future prediction leveraging synthetic trajectories. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp.6081-6088). New York : Institute of Electrical and Electronics Engineers Inc. [10.1109/ICPR48806.2021.9412158].
File in questo prodotto:
File Dimensione Formato  
Multiple_Future_Prediction_Leveraging_Synthetic_Trajectories.pdf

non disponibili

Tipologia: PDF editoriale
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 965.13 kB
Formato Adobe PDF
965.13 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/1224655